自由职业 AI 视觉创作者(拍摄与品牌故事)

This listing is synced directly from the company ATS.

Role Overview

This is a senior-level freelance role for an AI visual creator who will produce high-quality photos and videos for ads, website, social media, and product needs using cutting-edge AI tools like Kling, Sora 2, and ComfyUI. The hire will work closely with marketing and product teams to shape the brand's visual identity, design prompts and workflows, test new models, and build repeatable pipelines for consistent output. Impact includes enhancing the brand's storytelling and visual consistency across all AI-generated assets.

Perks & Benefits

This is a fully remote position with no specified time zone, offering flexibility for rapid experimentation and pushing new AI models to their limits. The role involves collaboration with marketing and product teams, providing opportunities for creative input and career growth in AI-driven visual production. While benefits are not detailed, typical freelance perks may include project-based autonomy and exposure to cutting-edge tools in a dynamic, innovative environment.

Full Job Description

我们正在寻找一位真正热爱并深度沉浸在 AI 图像和视频生成领域的人。

你需要非常熟悉当前的图像和视频生成技术生态,了解如何在不同系统中调教出特定的视觉效果,并能将抽象的想法快速产出为可用于实际生产的高质量图片和视频。你将与市场和产品团队紧密合作,利用最前沿的 AI 工具,共同塑造品牌的视觉风格。

如果你喜欢快速实验、探索新模型的极限,并能搭建稳定可复用的生成流程以持续输出高质量内容,你会非常适合这份工作。

要求

  • 深度使用过现代图像与视频模型(Kling、Nano Banana、Seedream、Hailuo、Sora 2 等)

  • 熟悉各大推理平台(Fal、Replicate、Krea、Florafauna、Weavy 等)及其能力范围

  • 能够通过 LoRA 等方法设计并优化 prompts、工作流以及生成管线,以实现特定视觉风格

  • 能在缺乏重度指示的情况下,快速产出精致、符合品牌调性的素材

  • 具备强烈的视觉识别力、构图能力与叙事能力

加分项(非必需)

  • 具备技术或软件工程背景

  • 熟练使用 ComfyUI(自部署或 Runpod 等环境皆可)

  • 会用 json 写提示词者优先

职责

  • 为广告、官网、社交媒体和产品场景生成高质量的图片和视频

  • 持续测试新模型与工作流,并将结果应用到创意生产管线中

  • 维持所有 AI 生成素材的一致性与质量标准

  • 与市场团队合作,使创意输出符合品牌方向与投放目标

  • 组织并交付规范、可复用的最终素材文件

We’re looking for someone who lives and breathes AI image and video gen

You should know the current image/video gen landscape cold, understand how to coax specific looks out of different systems, and be able to turn loose ideas into production-quality images and videos fast. You’ll work closely with our marketing and product teams to shape the visual identity of the brand using cutting-edge AI tools.

If you enjoy rapid experimentation, pushing new models to their limits, and building repeatable pipelines that deliver consistent, high-quality output, you’ll fit perfectly.

Requirements

  • Deep experience with modern image and video models (Kling, Nano Banana, Seedream, Hailuo, Sora 2, etc)

  • Strong familiarity with inference providers (Fal, Replicate, Krea, Florafauna, Weavy, etc) and their capabilities

  • Ability to design and refine prompts, workflows, and pipelines to achieve specific visual styles through LoRAs and other methods

  • Proven ability to deliver polished, on-brand assets quickly without heavy direction

  • Strong sense of visual identity, composition, and storytelling

Helpful but not required

  • Technical / software engineering background

  • Fluency with ComfyUI (self-hosted or Runpod/etc)

  • Prompting with json is a plus

Responsibilities

  • Produce high-quality photos and videos for ads, website, social, and product needs

  • Continuously test new models and workflows and apply improvements to our creative pipelines

  • Maintain consistency and quality across all AI-generated assets

  • Collaborate with marketing to align creative output with performance goals and brand direction

  • Organize and deliver production-ready files in clean, reusable formats

Similar jobs

Found 6 similar jobs